{"id":26878065,"url":"https://github.com/rohitl17/cab-dynamic-pricing","last_synced_at":"2025-05-07T17:21:02.578Z","repository":{"id":57416787,"uuid":"459456869","full_name":"rohitl17/cab-dynamic-pricing","owner":"rohitl17","description":"A web application for calculating dynamic price of Uber and Lyft cabs depending on various parameters with a feedback loop to retrain the models","archived":false,"fork":false,"pushed_at":"2022-03-18T22:08:38.000Z","size":97602,"stargazers_count":6,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-30T14:34:43.706Z","etag":null,"topics":["flask","machine-learning","python3","software-engineering"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rohitl17.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-02-15T06:34:19.000Z","updated_at":"2025-02-17T14:53:02.000Z","dependencies_parsed_at":"2022-08-29T19:42:11.468Z","dependency_job_id":null,"html_url":"https://github.com/rohitl17/cab-dynamic-pricing","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rohitl17%2Fcab-dynamic-pricing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rohitl17%2Fcab-dynamic-pricing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rohitl17%2Fcab-dynamic-pricing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rohitl17%2Fcab-dynamic-pricing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rohitl17","download_url":"https://codeload.github.com/rohitl17/cab-dynamic-pricing/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252922307,"owners_count":21825641,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["flask","machine-learning","python3","software-engineering"],"created_at":"2025-03-31T12:19:03.663Z","updated_at":"2025-05-07T17:21:02.555Z","avatar_url":"https://github.com/rohitl17.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"[![Build Status](https://app.travis-ci.com/rohitl17/cab-dynamic-pricing.svg?branch=main)](https://app.travis-ci.com/rohitl17/cab-dynamic-pricing) [![Coverage Status](https://coveralls.io/repos/github/rohitl17/cab-dynamic-pricing/badge.svg?branch=main)](https://coveralls.io/github/rohitl17/cab-dynamic-pricing?branch=main) ![contributors](https://img.shields.io/github/contributors/rohitl17/cab-dynamic-pricing.svg) ![codesize](https://img.shields.io/github/languages/code-size/rohitl17/cab-dynamic-pricing.svg)\n\n![logo file](/cab-dynamic-pricing/templates/logo.jpg)\n\n## Easy Cabs\nEasy Cabs is a ML-assisted web-based application which helps you in getting the dynamic pricing of Uber and Lyft cabs. The user enters the source and destination. Easy Cabs converts that to latitude, longitude, gets the weather information and predicts the estimated price for your rides using machine learning. The user can then make a decision on taking a cost-optimized cab.  \n \n## Background\nUber and Lyft account for the major market capitalization for offering cab services on an app. But these prices are not constant like public transportation. They are greatly affected by the demand and supply of rides at a given time. So what exactly drives this demand? Some of the factors include weather changes, rush hours and location. EasyCabs takes into account these factors and tries to replicate a prototypical version of the pricing and surging microservices for these apps. It also offers an opportunity to retrain models using a feedback loop as a separate microservice.\n\n\n## Authors\n- [Nayantara Mohan](https://github.com/nayantaramohan)  \n- [Rohit Lokwani](https://github.com/rohitl17)  \n- [Shubha Changappa Palachanda](https://github.com/shubha8196)\n\n\n## Project Distribution\n\n```\ncab-dynamic-pricing/\n  |- README.md\n  |- cab-dynamic-pricing/\n    |- __init__.py\n    |- configuration_files/\n      |- software_configuration_format.py\n    |- database/\n      |- users.csv\n    |- feedback_app/\n      |- training_testing_data/\n        |- lyft_test_mlr.csv\n        |- lyft_train_mlr.csv\n        |- testing_surge_price_classifier_df.csv\n        |- training_surge_price_classifier_df.csv\n        |- uber_test_mlr.csv\n        |- uber_train_mlr.csv\n      |- dynamic_price_model_training.py\n      |- surge_model_training.py\n      |- train_models.py\n    |- model_scripts/\n      |- dynamic_pricing_regression_inference.py\n      |- surge_classification_inference.py\n    |- model_weights/\n      |- lyft_mlr_model.sav\n      |- surge_classification_rf_model.sav\n      |- uber_mlr_model.sav\n    |- templates/\n      |- login_background.jpg\n      |- login_index.html\n      |- template_page2.html\n    |- tests/\n      |- test_app.py\n      |- test_dynamic_pricing_model_training.py\n      |- test_dynamic_pricing_regression_inference.py\n      |- test_geospatial_information.py\n      |- test_lyft.py\n      |- test_software_configuration_format.py\n      |- test_surge_classification_inference.py\n      |- test_surge_price_model.py\n      |- test_train_models.py\n      |- test_uber.py\n      |- test_user.py\n      |- test_weather_information.py\n    |- utils/\n      |- geospatial_information.py\n      |- lyft.py\n      |- uber.py\n      |- user.py\n      |- utils.py\n      |- weather_information.py\n    | - app.py\n  |- data/\n      |- cab_rides.csv.zipe\n      |- weather.csv\n  |- documentation/\n      |- api_documentation.md\n      |- component_specification.md\n      |- functional_specification.md\n      |- screenshots/\n  |- example\n      |- example.md\n      |- screenshots/\n  |- .coveragerc\n  |- .gitignore\n  |- LICENSE\n  |- requirements.txt\n  |- setup.py\n```\n  \n  \n## Data\n[Link to the Data Set](https://www.kaggle.com/ravi72munde/uber-lyft-cab-prices)   \nFeatures extracted from the dataset: -\n  - cab_type : Uber or Lyft.\n  - clouds : presence or absence of clouds.\n  - destination : name of the destination in words.\n  - humidity : humidity in percentage.\n  - location : location of the place where the weather is recorded.\n  - pressure : atmospheric pressure in millibar.\n  - price : price estimate for the ride in USD.\n  - rain : rain in inches for the last hour.\n  - name : type of the car specified, eg. X, XL.\n  - source : name of the source in words.\n  - surge_multiplier : 5 unique values mentioned. \n  - temp : temperature in Fahrenheit.\n  - time_stamp : start of the cab journey in epoch units.\n  - wind : wind speed in miles per hour.\n  \nNote: The data currently covers locations in Boston. Hence, to get relatively accurate estimates, the default models are bound to work the best for Boston locations.\n\n\n## Installation\n\nMethod 1: Cloning the Github Repository:\n\n1. Clone the repo\n```bash\ngit clone https://github.com/rohitl17/cab-dynamic-pricing.git\n```\n2. If you're using Anaconda, create and activate a new conda environment. For conda run\n```\nconda create -n cabdynamicpricing python=3.9\nconda activate cabdynamicpricing\n```\n\n  If you do not have anaconda, create a virtual environment in the root of the repo\n```bash\npython -m venv venv\nsource venv/bin/activate\n```\n\n3. Install the dependencies from the requirements.txt file using the below:\n```bash\npython -m pip install -r requirements.txt\n```\n\nMethod 2: Installing the package using the pip command:\n1. Run the following command to install the application\n```bash\npip install cab-dynamic-pricing\n```  \n2. Install the dependencies from the requirements.txt file using the below:\n```bash\npython -m pip install -r requirements.txt\n```\n\n\n## Usage and Output\n\nTo see how to use the package to get the dynamic pricing of Uber and Lyft, refer to the [example file](./examples/example.md)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frohitl17%2Fcab-dynamic-pricing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frohitl17%2Fcab-dynamic-pricing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frohitl17%2Fcab-dynamic-pricing/lists"}